Re: [PATCH 5/7] cxl: Add clear-error command

[Dave Jiang <dave.jiang@intel.com>]

On 1/9/26 9:07 AM, Ben Cheatham wrote:
> Add the 'cxl-clear-error' command. This command allows the user to clear
> device poison from CXL memory devices.
> 
> Signed-off-by: Ben Cheatham <Benjamin.Cheatham@amd.com>

Reviewed-by: Dave Jiang <dave.jiang@intel.com>


> ---
>  cxl/builtin.h      |  1 +
>  cxl/cxl.c          |  1 +
>  cxl/inject-error.c | 70 ++++++++++++++++++++++++++++++++++++++++++----
>  3 files changed, 67 insertions(+), 5 deletions(-)
> 
> diff --git a/cxl/builtin.h b/cxl/builtin.h
> index e82fcb5..68ed1de 100644
> --- a/cxl/builtin.h
> +++ b/cxl/builtin.h
> @@ -26,6 +26,7 @@ int cmd_enable_region(int argc, const char **argv, struct cxl_ctx *ctx);
>  int cmd_disable_region(int argc, const char **argv, struct cxl_ctx *ctx);
>  int cmd_destroy_region(int argc, const char **argv, struct cxl_ctx *ctx);
>  int cmd_inject_error(int argc, const char **argv, struct cxl_ctx *ctx);
> +int cmd_clear_error(int argc, const char **argv, struct cxl_ctx *ctx);
>  #ifdef ENABLE_LIBTRACEFS
>  int cmd_monitor(int argc, const char **argv, struct cxl_ctx *ctx);
>  #else
> diff --git a/cxl/cxl.c b/cxl/cxl.c
> index a98bd6b..e1740b5 100644
> --- a/cxl/cxl.c
> +++ b/cxl/cxl.c
> @@ -81,6 +81,7 @@ static struct cmd_struct commands[] = {
>  	{ "destroy-region", .c_fn = cmd_destroy_region },
>  	{ "monitor", .c_fn = cmd_monitor },
>  	{ "inject-error", .c_fn = cmd_inject_error },
> +	{ "clear-error", .c_fn = cmd_clear_error },
>  };
>  
>  int main(int argc, const char **argv)
> diff --git a/cxl/inject-error.c b/cxl/inject-error.c
> index 0ca2e6b..76f9fa9 100644
> --- a/cxl/inject-error.c
> +++ b/cxl/inject-error.c
> @@ -17,6 +17,10 @@ static struct inject_params {
>  	const char *address;
>  } inj_param;
>  
> +static struct clear_params {
> +	const char *address;
> +} clear_param;
> +
>  static const struct option inject_options[] = {
>  	OPT_STRING('t', "type", &inj_param.type, "Error type",
>  		   "Error type to inject into <device>"),
> @@ -28,6 +32,15 @@ static const struct option inject_options[] = {
>  	OPT_END(),
>  };
>  
> +static const struct option clear_options[] = {
> +	OPT_STRING('a', "address", &clear_param.address, "Address for poison clearing",
> +		   "Device physical address to clear poison from in hex or decimal"),
> +#ifdef ENABLE_DEBUG
> +	OPT_BOOLEAN(0, "debug", &debug, "turn on debug output"),
> +#endif
> +	OPT_END(),
> +};
> +
>  static struct log_ctx iel;
>  
>  static struct cxl_protocol_error *find_cxl_proto_err(struct cxl_ctx *ctx,
> @@ -100,7 +113,7 @@ static int inject_proto_err(struct cxl_ctx *ctx, const char *devname,
>  }
>  
>  static int poison_action(struct cxl_ctx *ctx, const char *filter,
> -			 const char *addr_str)
> +			 const char *addr_str, bool clear)
>  {
>  	struct cxl_memdev *memdev;
>  	unsigned long long addr;
> @@ -128,12 +141,18 @@ static int poison_action(struct cxl_ctx *ctx, const char *filter,
>  		return -EINVAL;
>  	}
>  
> -	rc = cxl_memdev_inject_poison(memdev, addr);
> +	if (clear)
> +		rc = cxl_memdev_clear_poison(memdev, addr);
> +	else
> +		rc = cxl_memdev_inject_poison(memdev, addr);
> +
>  	if (rc)
> -		log_err(&iel, "failed to inject poison at %s:%s: %s\n",
> +		log_err(&iel, "failed to %s %s:%s: %s\n",
> +			clear ? "clear poison at" : "inject poison at",
>  			cxl_memdev_get_devname(memdev), addr_str, strerror(-rc));
>  	else
> -		log_info(&iel, "poison injected at %s:%s\n",
> +		log_info(&iel,
> +			 "poison %s at %s:%s\n", clear ? "cleared" : "injected",
>  			 cxl_memdev_get_devname(memdev), addr_str);
>  
>  	return rc;
> @@ -165,7 +184,7 @@ static int inject_action(int argc, const char **argv, struct cxl_ctx *ctx,
>  	}
>  
>  	if (strcmp(inj_param.type, "poison") == 0) {
> -		rc = poison_action(ctx, argv[0], inj_param.address);
> +		rc = poison_action(ctx, argv[0], inj_param.address, false);
>  		return rc;
>  	}
>  
> @@ -186,3 +205,44 @@ int cmd_inject_error(int argc, const char **argv, struct cxl_ctx *ctx)
>  
>  	return rc ? EXIT_FAILURE : EXIT_SUCCESS;
>  }
> +
> +static int clear_action(int argc, const char **argv, struct cxl_ctx *ctx,
> +			const struct option *options, const char *usage)
> +{
> +	const char * const u[] = {
> +		usage,
> +		NULL
> +	};
> +	int rc = -EINVAL;
> +
> +	log_init(&iel, "cxl clear-error", "CXL_CLEAR_LOG");
> +	argc = parse_options(argc, argv, options, u, 0);
> +
> +	if (debug) {
> +		cxl_set_log_priority(ctx, LOG_DEBUG);
> +		iel.log_priority = LOG_DEBUG;
> +	} else {
> +		iel.log_priority = LOG_INFO;
> +	}
> +
> +	if (argc != 1) {
> +		usage_with_options(u, options);
> +		return rc;
> +	}
> +
> +	rc = poison_action(ctx, argv[0], clear_param.address, true);
> +	if (rc) {
> +		log_err(&iel, "Failed to clear poison on %s at: %s\n",
> +			argv[0], strerror(-rc));
> +		return rc;
> +	}
> +
> +	return rc;
> +}
> +
> +int cmd_clear_error(int argc, const char **argv, struct cxl_ctx *ctx)
> +{
> +	int rc = clear_action(argc, argv, ctx, clear_options,
> +			      "clear-error <device> [<options>]");
> +	return rc ? EXIT_FAILURE : EXIT_SUCCESS;
> +}